arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.06993cs.CV
收藏

通过深度卷积网络减少压缩伪影

Compression Artifacts Reduction by a Deep Convolutional Network

The Chinese University of Hong Kong(香港中文大学)

Chao Dong, Yubin Deng, Chen Change Loy, Xiaoou Tang

摘要:

有损压缩引入了复杂的压缩伪像,特别是块伪像、振铃效应和模糊。现有的算法要么专注于去除块效应并产生模糊的输出,要么恢复伴随着振铃效应的锐化图像。受超分辨率深度卷积网络(DCN)的启发,我们制定了一个紧凑而高效的网络,用于无缝衰减不同的压缩伪影。我们还证明,可以使用在浅层网络中学习的特征有效地训练更深层次的模型。遵循类似的“从易到难”的思路,我们系统地研究了几种实际的迁移设置,并展示了迁移学习在低水平视觉问题中的有效性。我们的方法在基准数据集和真实用例(即Twitter)上都显示出比最先进的性能更优越的性能。此外,我们表明,我们的方法可以作为预处理,以方便其他低层次的视觉例程时,他们采取压缩图像作为输入。

英文摘要:

Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restores sharpened images that are accompanied with ringing effects. Inspired by the deep convolutional networks (DCN) on super-resolution, we formulate a compact and efficient network for seamless attenuation of different compression artifacts. We also demonstrate that a deeper model can be effectively trained with the features learned in a shallow network. Following a similar "easy to hard" idea, we systematically investigate several practical transfer settings and show the effectiveness of transfer learning in low-level vision problems. Our method shows superior performance than the state-of-the-arts both on the benchmark datasets and the real-world use case (i.e. Twitter). In addition, we show that our method can be applied as pre-processing to facilitate other low-level vision routines when they take compressed images as input.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑